Small and Practical BERT Models for Sequence Labeling
Autor: | Naveen Arivazhagan, Amelia Archer, Melvin Johnson, Henry Tsai, Xin Li, Jason Riesa |
---|---|
Rok vydání: | 2019 |
Předmět: |
FOS: Computer and information sciences
Scheme (programming language) Computer Science - Computation and Language Computer science 02 engineering and technology 010501 environmental sciences 01 natural sciences Sequence labeling 0202 electrical engineering electronic engineering information engineering 020201 artificial intelligence & image processing State (computer science) Baseline (configuration management) Computation and Language (cs.CL) computer Algorithm 0105 earth and related environmental sciences computer.programming_language |
Zdroj: | EMNLP/IJCNLP (1) |
Popis: | We propose a practical scheme to train a single multilingual sequence labeling model that yields state of the art results and is small and fast enough to run on a single CPU. Starting from a public multilingual BERT checkpoint, our final model is 6x smaller and 27x faster, and has higher accuracy than a state-of-the-art multilingual baseline. We show that our model especially outperforms on low-resource languages, and works on codemixed input text without being explicitly trained on codemixed examples. We showcase the effectiveness of our method by reporting on part-of-speech tagging and morphological prediction on 70 treebanks and 48 languages. 11 pages including appendices; accepted to appear at EMNLP-IJCNLP 2019 |
Databáze: | OpenAIRE |
Externí odkaz: |